talk-stage4-position

Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory CHECKPOINT for user confirmation before scripting. Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body has strong workflow clarity with an explicit mandatory checkpoint, validation checklist, and anti-patterns, but is weakened by verbose inline output templates and a missing referenced bundle file (templates/feedback-draft.md). Actionability is moderate because concrete guidance is largely placeholder scaffolding rather than executable instruction.

Suggestions

Move the large inline markdown format templates (angles.md, titre.md, descriptions.md) into separate reference files and link to them one level deep, keeping only a concise overview in SKILL.md.

Add the missing templates/feedback-draft.md bundle file so the referenced peer feedback template actually exists, or remove the reference.

Tighten the output-format placeholders into concrete, reusable instructions so the guidance is actionable rather than fill-in-the-blank scaffolding.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient and assumes Claude's competence, but the full inline markdown templates for angles.md, titre.md, and descriptions.md are lengthy scaffolding that could live in bundle files. It is not a 3 because there is notable template bulk that pads the context window.	2 / 3
Actionability	It provides concrete templates and a literal CHECKPOINT message to display, but the output formats are heavy on placeholders (e.g. '{provisional title}', '{strength 1}') and lack executable commands, leaving key generation details to inference rather than instruction.	2 / 3
Workflow Clarity	Clear numbered sequence (1-8), an explicit mandatory CHECKPOINT with 'Do not invoke Stage 5 without explicit user confirmation', a validation checklist, and an anti-patterns section providing error-recovery guidance for the pipeline's riskiest control point.	3 / 3
Progressive Disclosure	Sections are well-organized and reference templates/feedback-draft.md, but that referenced file is not present in the bundle, and the large inline markdown format templates (angles/titre/descriptions) would be better split into one-level-deep reference files rather than embedded inline.	2 / 3
	Total	9 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, action-oriented, and includes an explicit 'Use when' trigger clause covering framing, CFP prep, and angle selection. It would benefit from a broader set of natural trigger terms users might actually say.

Suggestions

Add common natural trigger phrases users would say, such as 'talk proposal', 'conference abstract', 'call for papers', or 'pitch a talk'.

Consider whether 'strategic talk angles' is jargon a user would actually say; plainer phrasing like 'framing a conference talk' may improve trigger term quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft', then 'enforces a mandatory CHECKPOINT'.	3 / 3
Completeness	Clearly answers both what it does and when to use it via the explicit 'Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles' clause.	3 / 3
Trigger Term Quality	Includes some natural terms ('CFP submission', 'narrative angles') but lacks common variations users would actually say like 'talk proposal', 'conference talk', 'abstract', or 'call for papers'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (talk framing/CFP positioning) with triggers specific enough that it is unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: FlorianBruniaux/claude-code-ultimate-guide
Commit: eb4fbbd

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.